Senior ML Platform Engineer — Scalable Inference

Atlassian; Amsterdam; Ibrido; EUR 120.000 - 180.000; Tempo pieno

Vantaggi offerti da questo lavoro

Health resources

Volunteer days

Community engagement

Descrizione del lavoro

Atlassian's AI & ML Platform is seeking a Senior ML System Engineer to design and optimize large-scale model serving systems end-to-end. You’ll own distributed infrastructure, from global KV cache to batching, and will work on low-level GPU kernels and quantization.

On day one, expect 5+ years in software engineering, 2+ years in performance optimization, strong C/C++ or Rust, and experience with high-concurrency production serving and GPU inference engines.

Competenze

• 5+ years of software engineering experience with system-level focus.
• Deep expertise in low-level systems programming and performance tuning.
• Experience with large-scale model serving and high concurrency environments.

Mansioni

• Architect scalable distributed infrastructure for model serving, including load balancing and auto-scaling.
• Optimize latency and throughput under production workloads.
• Build reliable, high-concurrency serving systems handling billions of requests.
• Benchmark, tune, and accelerate inference engines.
• Create robust CI/CD pipelines for deployment and updates.
• Collaborate with senior ML engineers to fine-tune open-source LLMs.

Conoscenze

Distributed systems

Low-level programming

Performance optimization

GPU inference

High concurrency

Strumenti

C/C++

Rust

vLLM

SGLang

Triton

TensorRT-LLM

Descrizione del lavoro

Atlassian's AI & ML Platform is seeking a Senior ML System Engineer to design and optimize large-scale model serving systems end-to-end. You’ll own distributed infrastructure, from global KV cache to batching, and will work on low-level GPU kernels and quantization.

On day one, expect 5+ years in software engineering, 2+ years in performance optimization, strong C/C++ or Rust, and experience with high-concurrency production serving and GPU inference engines.